Driving · 2026-10-08
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
Rajneesh Anand, Mayuresh V. Kothare
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors introduce DropletRunner, a robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning. A DreamerV3-based policy is trained offline on experimental data (no simulator or analytical model), transfers zero-shot to unseen geometries, and autonomously discovers an oscillatory depinning strategy when the droplet sticks. The full training pipeline takes under 90 minutes.
Why it matters
The work targets automated physical manipulation of deformable soft matter in self-driving laboratories, specifically autonomous droplet transport on an open surface where interfacial physics create partially observable, nonlinear, history-dependent dynamics. The authors report zero-shot transfer to new geometries, an emergent depinning behavior (not reward-shaped or programmed), and a short end-to-end training time, supported by a source-code release for autonomous droplet navigation.
Method
- DropletRunner: a 3D-printed PLA board with two-axis motor actuation that tilts a silicone-oil-coated channel while an overhead camera provides visual feedback.
- Model-based RL uses DreamerV3 trained fully offline on experimental data, without any simulator or analytical model.
- A learned policy is evaluated across multiple channel geometries and compared to an optimized PID baseline on the same hardware.
Abstract (from arXiv)
Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms. A critical instance is autonomous droplet transport on an open surface, where contact-angle hysteresis, capillary pinning, and surface heterogeneity produce partially observable dynamics that pose significant challenges for classical model-based controllers. We introduce the first robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning. A two-axis tilting board coated with a thin silicone oil film drives the droplet, while an overhead camera provides real-time feedback. A learned policy was trained on just 50 to 150 physical episodes depending on geometric complexity, without simulation or analytical models. Beyond performance alone, the platform demonstrates three capabilities of interest to the SDL community: it robustly transfers zero-shot to unseen geometries; it autonomously discovers an oscillatory depinning strategy to free the droplet when it sticks; and it completes its full training pipeline in under 90 minutes. These results extend reinforcement-learning manipulation from rigid microrobots to deformable soft-matter systems for next-generation SDLs.
Related papers
- Generative World Models Enable Predictive Control of Laser Melt Pool Dynamics
- GPWM: Modeling the World as 3D Particle Motion
- ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control
- ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation
- EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-03 · Indexed by Pub-AI: 2026-10-08 UTC
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
Preprint posted: 2026-10-03 · Original record ↗
- arxiv
- 2610.08852
Explicit source versions (1)
- v1 · 2026-10-03
- Preprint available
Source date: 2026-10-03 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms. A critical instance is autonomous droplet transport on an open surface, where contact-angle hysteresis, capillary pinning, and surface heterogeneity produce partially observable dynamics that pose significant challenges for classical model-based controllers. We introduce the first robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning. A two-axis tilting board coated with a thin silicone oil film drives the droplet, while an overhead camera provides real-time feedback. A learned policy was trained on just 50 to 150 physical episodes depending on geometric complexity, without simulation or analytical models. Beyond performance alone, the platform demonstrates three capabilities of interest to the SDL community: it robustly transfers zero-shot to unseen geometries; it autonomously discovers an oscillatory depinning strategy to free the droplet when it sticks; and it completes its full training pipeline in under 90 minutes. These results extend reinforcement-learning manipulation from rigid microrobots to deformable soft-matter systems for next-generation SDLs.
